# ICASSP 2021 Deep Noise Suppression Challenge

arXiv: https://arxiv.org/abs/2009.06122 · HTML: https://mlsanity.com/paper/2009.06122/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 27 of 27)

- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Interspeech 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2101.01902/) (2021)
- [AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement](https://mlsanity.com/paper/2501.15417/) (2025)
- [Sylber: Syllabic Embedding Representation of Speech from Raw Audio](https://mlsanity.com/paper/2410.07168/) (2024)
- [Real-time Denoising and Dereverberation with Tiny Recurrent U-Net](https://mlsanity.com/paper/2102.03207/) (2021)
- [ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding](https://mlsanity.com/paper/2207.09514/) (2022)
- [End-to-End Neural Speech Coding for Real-Time Communications](https://mlsanity.com/paper/2201.09429/) (2022)
- [Latent-Domain Predictive Neural Speech Coding](https://mlsanity.com/paper/2207.08363/) (2022)
- [AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement](https://mlsanity.com/paper/2309.08030/) (2023)
- [Cross-Scale Vector Quantization for Scalable Neural Speech Coding](https://mlsanity.com/paper/2207.03067/) (2022)
- [A Mask Free Neural Network for Monaural Speech Enhancement](https://mlsanity.com/paper/2306.04286/) (2023)
- [HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing](https://mlsanity.com/paper/2407.07566/) (2024)
- [Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity](https://mlsanity.com/paper/2502.01330/) (2025)
- [Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations](https://mlsanity.com/paper/2503.12115/) (2025)
- [PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction](https://mlsanity.com/paper/2110.00940/) (2021)
- [Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression](https://mlsanity.com/paper/2308.11053/) (2023)
- [CheapNET: Improving Light-weight speech enhancement network by projected loss function](https://mlsanity.com/paper/2311.15959/) (2023)
- [NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion](https://mlsanity.com/paper/2511.00256/) (2025)
- [Sylber 2.0: A Universal Syllable Embedding](https://mlsanity.com/paper/2601.22306/) (2026)
- [Training-Free Multi-Step Audio Source Separation](https://mlsanity.com/paper/2505.19534/) (2025)
- [Quaternion Self-Attention with Shared Scores](https://mlsanity.com/paper/2605.24920/) (2026)
- [Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge](https://mlsanity.com/paper/2402.01413/) (2024)
- [TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition](https://mlsanity.com/paper/2404.12979/) (2024)
- [How much to Dereverberate? Low-Latency Single-Channel Speech Enhancement in Distant Microphone Scenarios](https://mlsanity.com/paper/2505.01338/) (2025)
- [Text-Queried Audio Source Separation via Hierarchical Modeling](https://mlsanity.com/paper/2505.21025/) (2025)
- [Performance and Complexity Trade-off Optimization of Speech Models During Training](https://mlsanity.com/paper/2601.13704/) (2026)
- [StreamAlign: Streaming Text-Aligned Speech Tokenization](https://mlsanity.com/paper/2609.09719/) (2026)

## Abstract (arXiv)

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH 2020. We open sourced training and test datasets for researchers to train their noise suppression models. We also open sourced a subjective evaluation framework and used the tool to evaluate and pick the final winners. Many researchers from academia and industry made significant contributions to push the field forward. We also learned that as a research community, we still have a long way to go in achieving excellent speech quality in challenging noisy real-time conditions. In this challenge, we are expanding both our training and test datasets. There are two tracks with one focusing on real-time denoising and the other focusing on real-time personalized deep noise suppression. We also make a non-intrusive objective speech quality metric called DNSMOS available for participants to use during their development stages. The final evaluation will be based on subjective tests.